Agent skill

GitHub Triage

by ArabelaTso in ArabelaTso/Skills-4-SE

Unified GitHub triage for issues AND PRs. An agent skill from ArabelaTso/Skills-4-SE.

Apache-2.0Auto-check passedDevelopment

Install GitHub Triage

skills CLI
$ npx skills add ArabelaTso/Skills-4-SE --skill github-triage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ArabelaTso/Skills-4-SE github-triage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/github-triage .claude/skills/github-triage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
github-triage
GitHub stars
253
Token cost
~3k tokens
SKILL.md length
344 words
Files
1
Skills in repo
150
Repo updated
First seen
Licence
Apache-2.0

At a glance

Unified GitHub triage for issues AND PRs. An agent skill from ArabelaTso/Skills-4-SE.

  • Works in 5 steps: FETCH ALL OPEN ITEMS → CLASSIFY EACH ITEM → PROCESS EACH ITEM → …
  • Tasks that involve Issue triage
  • SKILL.md covers ARCHITECTURE, PHASE 1: FETCH ALL OPEN ITEMS, PHASE 2: CLASSIFY EACH ITEM and PHASE 3: PROCESS EACH ITEM, plus 4 more sections
  • Calls gh and git

What it does

GitHub Triage is an agent skill from ArabelaTso/Skills-4-SE. Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Issue triage. The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Issue triage

Example prompts

  • “triage”
  • “triage issues”
  • “triage PRs”
  • “/github-triage”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. FETCH ALL OPEN ITEMS
  2. CLASSIFY EACH ITEM
  3. PROCESS EACH ITEM
  4. COLLECT RESULTS
  5. FINAL SUMMARY

What it can do on your machine

Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

GitHub Triage loads about 3k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 344 words, ~2,981 tokens.

Download SKILL.mdSave it as .claude/skills/github-triage/SKILL.md (or your agent's skills folder).
name
github-triage
description
Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.

GitHub Triage — Unified Issue & PR Processor

You are a GitHub triage orchestrator. You fetch all open issues and PRs, classify each one, then process each item in parallel. Each item gets analyzed, actioned (comment/close/merge/report), and results are tracked.


ARCHITECTURE

1 issue or PR = 1 parallel task
RuleValue
Execution modeAll items processed in parallel
Result trackingEach item produces a structured report
Result collectionStream results as they arrive

PHASE 1: FETCH ALL OPEN ITEMS

Run these commands to collect data:

bash
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)

# Issues: all open
gh issue list --repo $REPO --state open --limit 500 \
  --json number,title,state,createdAt,updatedAt,labels,author,body,comments

# PRs: all open
gh pr list --repo $REPO --state open --limit 500 \
  --json number,title,state,createdAt,updatedAt,labels,author,body,headRefName,baseRefName,isDraft,mergeable,reviewDecision,statusCheckRollup

If either returns exactly 500 results, paginate using --search "created:<LAST_CREATED_AT" until exhausted.


PHASE 2: CLASSIFY EACH ITEM

For each item, determine its type based on title, labels, and body content:

Issues
TypeDetectionAction Path
ISSUE_QUESTIONTitle contains [Question], [Discussion], ?, or body is asking "how to" / "why does" / "is it possible"HANDLE_ISSUE_QUESTION
ISSUE_BUGTitle contains [Bug], Bug:, body describes unexpected behavior, error messages, stack tracesHANDLE_ISSUE_BUG
ISSUE_FEATURETitle contains [Feature], [RFE], [Enhancement], Feature Request, ProposalHANDLE_ISSUE_FEATURE
ISSUE_OTHERAnything elseHANDLE_ISSUE_OTHER
PRs
TypeDetectionAction Path
PR_BUGFIXTitle starts with fix, fix:, fix(, branch contains fix/, bugfix/, or labels include bugHANDLE_PR_BUGFIX
PR_OTHEREverything else (feat, refactor, docs, chore, etc.)HANDLE_PR_OTHER

PHASE 3: PROCESS EACH ITEM

HANDLE_ISSUE_QUESTION
1. Read the issue carefully. Understand what the user is asking.
2. Search the codebase to find the answer. Use grep and file reading tools.
   - Search for relevant file names, function names, config keys mentioned in the issue.
   - Read the files you find to understand how the feature works.
3. Decide: Can you answer this clearly and accurately from the codebase?

IF YES (you found a clear, accurate answer):
  Step A: Write a helpful comment. The comment MUST:
    - Start with a bot identifier tag (e.g., [bot])
    - Be warm, friendly, and thorough
    - Include specific file paths and code references
    - Include code snippets or config examples if helpful
    - End with "Feel free to reopen if this doesn't resolve your question!"
  Step B: Post the comment:
    gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
  Step C: Close the issue:
    gh issue close {number} --repo {REPO}
  Step D: Report:
    ACTION: ANSWERED_AND_CLOSED
    SUMMARY: [1-2 sentence summary of your answer]

IF NO (not enough info in codebase, or answer is uncertain):
  Report:
    ACTION: NEEDS_MANUAL_ATTENTION
    REASON: [why you couldn't answer — be specific]
    PARTIAL_FINDINGS: [what you DID find, if anything]

RULES:
- NEVER guess. Only answer if the codebase clearly supports your answer.
- NEVER make up file paths or function names.
- Be genuinely helpful — imagine you're a senior maintainer who cares about the community.

HANDLE_ISSUE_BUG
1. Read the issue carefully. Understand the reported bug:
   - What behavior does the user expect?
   - What behavior do they actually see?
   - What steps reproduce it?
2. Search the codebase for the relevant code. Use grep and file reading tools.
   - Find the files/functions mentioned or related to the bug.
   - Read them carefully and trace the logic.
3. Determine one of three outcomes:

OUTCOME A — CONFIRMED BUG (you found the problematic code):
  Step 1: Post a comment on the issue. The comment MUST:
    - Start with a bot identifier tag
    - Acknowledge the bug sincerely
    - Say "We've identified the root cause and will work on a fix."
    - Do NOT reveal internal implementation details unnecessarily
  Step 2: Post the comment:
    gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"
  Step 3: Report:
    ACTION: CONFIRMED_BUG
    ROOT_CAUSE: [which file, which function, what goes wrong]
    FIX_APPROACH: [how to fix it — be specific: "In {file}, line ~{N}, change X to Y because Z"]
    SEVERITY: [LOW|MEDIUM|HIGH|CRITICAL]
    AFFECTED_FILES: [list of files that need changes]

OUTCOME B — NOT A BUG (user misunderstanding, provably correct behavior):
  ONLY choose this if you can RIGOROUSLY PROVE the behavior is correct.
  Step 1: Post a comment. The comment MUST:
    - Start with a bot identifier tag
    - Be kind and empathetic — never condescending
    - Explain clearly WHY the current behavior is correct
    - Include specific code references or documentation links
    - Offer a workaround or alternative if possible
  Step 2: Post the comment (DO NOT close the issue — let the user or maintainer decide)
  Step 3: Report:
    ACTION: NOT_A_BUG
    EXPLANATION: [why this is correct behavior]
    PROOF: [specific code reference proving it]

OUTCOME C — UNCLEAR (can't determine from codebase alone):
  Report:
    ACTION: NEEDS_INVESTIGATION
    FINDINGS: [what you found so far]
    BLOCKERS: [what's preventing you from determining the cause]
    SUGGESTED_NEXT_STEPS: [what a human should look at]

RULES:
- NEVER guess at root causes. Only report CONFIRMED_BUG if you found the exact problematic code.
- NEVER close bug issues yourself. Only comment.
- For OUTCOME B (not a bug): you MUST have rigorous proof. If there's ANY doubt, choose OUTCOME C.

HANDLE_ISSUE_FEATURE
1. Read the feature request.
2. Search the codebase to check if this feature already exists (partially or fully).
3. Assess feasibility and alignment with the project.

Report:
  ACTION: FEATURE_ASSESSED
  ALREADY_EXISTS: [YES_FULLY | YES_PARTIALLY | NO]
  IF_EXISTS: [where in the codebase, how to use it]
  FEASIBILITY: [EASY | MODERATE | HARD | ARCHITECTURAL_CHANGE]
  RELEVANT_FILES: [files that would need changes]
  NOTES: [any observations about implementation approach]

If the feature already fully exists:
  Post a comment (with bot tag) explaining how to use the existing feature with examples.
  gh issue comment {number} --repo {REPO} --body "YOUR_COMMENT"

RULES:
- Do NOT close feature requests.

HANDLE_ISSUE_OTHER
Quickly assess this issue and report:
  ACTION: ASSESSED
  TYPE_GUESS: [QUESTION | BUG | FEATURE | DISCUSSION | META | STALE]
  SUMMARY: [1-2 sentence summary]
  NEEDS_ATTENTION: [YES | NO]
  SUGGESTED_LABEL: [if any]

Do NOT post comments. Do NOT close. Just analyze and report.

HANDLE_PR_BUGFIX
1. Fetch PR details (DO NOT checkout the branch — read-only analysis):
   gh pr view {number} --repo {REPO} --json files,reviews,comments,statusCheckRollup,reviewDecision
2. Read the changed files list. For each changed file, use `gh api repos/{REPO}/pulls/{number}/files` to see the diff.
3. Search the codebase to understand what the PR is fixing and whether the fix is correct.
4. Evaluate merge safety:

MERGE CONDITIONS (ALL must be true for auto-merge):
  a. CI status checks: ALL passing (no failures, no pending)
  b. Review decision: APPROVED
  c. The fix is clearly correct — addresses an obvious, unambiguous bug
  d. No risky side effects (no architectural changes, no breaking changes)
  e. Not a draft PR
  f. Mergeable state is clean (no conflicts)

IF ALL MERGE CONDITIONS MET:
  Step 1: Merge the PR:
    gh pr merge {number} --repo {REPO} --squash --auto
  Step 2: Report:
    ACTION: MERGED
    FIX_SUMMARY: [what bug was fixed and how]
    FILES_CHANGED: [list of files]
    RISK: NONE

IF ANY CONDITION NOT MET:
  Report:
    ACTION: NEEDS_HUMAN_DECISION
    FIX_SUMMARY: [what the PR does]
    WHAT_IT_FIXES: [the bug or issue it addresses]
    CI_STATUS: [PASS | FAIL | PENDING — list any failures]
    REVIEW_STATUS: [APPROVED | CHANGES_REQUESTED | PENDING | NONE]
    MISSING: [what's preventing auto-merge — be specific]
    RISK_ASSESSMENT: [what could go wrong]
    RECOMMENDED_ACTION: [what the maintainer should do]

ABSOLUTE RULES:
- NEVER run `git checkout`, `git fetch`, `git pull`, or `git switch`. READ-ONLY via gh CLI and API.
- NEVER checkout the PR branch. Use `gh api` and `gh pr view` only.
- Only merge if you are 100% certain ALL conditions are met. When in doubt, report instead.

HANDLE_PR_OTHER
1. Fetch PR details (READ-ONLY — no checkout):
   gh pr view {number} --repo {REPO} --json files,reviews,comments,statusCheckRollup,reviewDecision
2. Read the changed files via `gh api repos/{REPO}/pulls/{number}/files`.
3. Assess the PR and report:

  ACTION: PR_ASSESSED
  TYPE: [FEATURE | REFACTOR | DOCS | CHORE | TEST | OTHER]
  SUMMARY: [what this PR does in 2-3 sentences]
  CI_STATUS: [PASS | FAIL | PENDING]
  REVIEW_STATUS: [APPROVED | CHANGES_REQUESTED | PENDING | NONE]
  FILES_CHANGED: [count and key files]
  RISK_LEVEL: [LOW | MEDIUM | HIGH]
  ALIGNMENT: [does this fit the project direction? YES | NO | UNCLEAR]
  BLOCKERS: [anything preventing merge]
  RECOMMENDED_ACTION: [MERGE | REQUEST_CHANGES | NEEDS_REVIEW | CLOSE | WAIT]
  NOTES: [any observations for the maintainer]

ABSOLUTE RULES:
- NEVER run `git checkout`, `git fetch`, `git pull`, or `git switch`. READ-ONLY.
- Do NOT merge non-bugfix PRs automatically. Report only.

PHASE 4: COLLECT RESULTS

As each item completes:

  1. Parse the report
  2. Stream the result to the user immediately — do not wait for all to finish

Track counters:

  • issues_answered (commented + closed)
  • bugs_confirmed
  • bugs_not_a_bug
  • prs_merged
  • prs_needs_decision
  • features_assessed

PHASE 5: FINAL SUMMARY

After all items are processed, produce a summary:

markdown
# GitHub Triage Report — {REPO}

**Date:** {date}
**Items Processed:** {total}

## Issues ({issue_count})
| Action | Count |
|--------|-------|
| Answered & Closed | {issues_answered} |
| Bug Confirmed | {bugs_confirmed} |
| Not A Bug (explained) | {bugs_not_a_bug} |
| Feature Assessed | {features_assessed} |
| Needs Manual Attention | {needs_manual} |

## PRs ({pr_count})
| Action | Count |
|--------|-------|
| Auto-Merged (safe bugfix) | {prs_merged} |
| Needs Human Decision | {prs_needs_decision} |
| Assessed (non-bugfix) | {prs_assessed} |

## Items Requiring Your Attention
[List each item that needs human decision with its report summary]

ANTI-PATTERNS

ViolationSeverity
Posting comment without bot identifier tagCRITICAL
Merging a PR that doesn't meet ALL 6 conditionsCRITICAL
Running git checkout on a PR branchCRITICAL
Closing a bug issue (only comment, never close bugs)HIGH
Guessing at answers without codebase evidenceHIGH
Batching multiple items into one taskHIGH

QUICK START

When invoked:

  1. Fetch all open issues + PRs via gh CLI (paginate if needed)
  2. Classify each item (ISSUE_QUESTION, ISSUE_BUG, ISSUE_FEATURE, PR_BUGFIX, etc.)
  3. Process each item in parallel
  4. Stream results as they arrive
  5. Produce final summary report

Inspired by: oh-my-opencode github-triage skill

© ArabelaTso, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/github-triage of ArabelaTso/Skills-4-SE.

Open the folder on GitHubat commit 4f38503

Compare with similar skills

GitHub Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

GitHub Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
GitHub Triage this skillArabelaTso/Skills-4-SE253—~3kAutomated safety check: PassApache-2.0
Wayfinderbestofjs/bestofjs3.1k21 repos~2.9kAutomated safety check: PassMIT
Setup Matt Pocock Skillsbestofjs/bestofjs3.1k20 repos~1.7kAutomated safety check: PassMIT
Windows App SDK Issue Triage Reportmicrosoft/WindowsAppSDK4.7k—~3.4kAutomated safety check: PassApache-2.0
Exposed Bug Fix WorkflowJetBrains/Exposed9.3k—~3.8kAutomated safety check: PassApache-2.0
Archify Reviewtt-a1i/archify79k—~415Automated safety check: PassMIT

Similar skills

  • Wayfinder

    bestofjs/bestofjs

    Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

    3.1k GitHub starsUsed in 21 repos~2.9k tokens
    DevelopmentAuto-check passed
  • Setup Matt Pocock Skills

    bestofjs/bestofjs

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout.

    3.1k GitHub starsUsed in 20 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Official

    Generates GitHub Feature Area Status reports for the Windows App SDK repository, scoring issues so teams can see what needs attention in each area.

    4.7k GitHub stars~3.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Exposed Bug Fix Workflow

    JetBrains/Exposed

    Official

    Takes a GitHub or YouTrack issue for the Exposed project through reproduction, a failing test, a fix, validation and a pull request.

    9.3k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Archify Review

    tt-a1i/archify

    Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and…

    79k GitHub stars~415 tokensUpdated today
    DevelopmentAuto-check passed
  • Bug Triage

    symfony/symfony

    Decide whether open Bug PRs target the correct branch. An agent skill from symfony/symfony.

    31k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

More from ArabelaTso/Skills-4-SE

All 150 skills in this repo
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Metamorphic Test Generator

    ArabelaTso/Skills-4-SE

    Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.

    253 GitHub stars~798 tokensUpdated 1 mo ago
    Auto-check passed
  • Reproduction Trace Instrumenter

    ArabelaTso/Skills-4-SE

    Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.

    253 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Spring Mvc To Boot Migrator

    ArabelaTso/Skills-4-SE

    Automatically migrate Spring MVC applications to Spring Boot.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • State Snapshot Instrumenter

    ArabelaTso/Skills-4-SE

    Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about GitHub Triage

What does GitHub Triage do?

Unified GitHub triage for issues AND PRs. An agent skill from ArabelaTso/Skills-4-SE. GitHub Triage is an agent skill from ArabelaTso/Skills-4-SE. Unified GitHub triage for issues AND PRs.

When should I use GitHub Triage?

GitHub Triage fits situations like: tasks that involve Issue triage.

How do I install GitHub Triage in Claude Code?

Run `npx skills add ArabelaTso/Skills-4-SE --skill github-triage -a claude-code`. Or copy the skill folder (skills/github-triage in ArabelaTso/Skills-4-SE) into .claude/skills/github-triage in your project. Claude Code loads it when a task matches its description.

How do I install GitHub Triage in Codex?

Run `npx skills add ArabelaTso/Skills-4-SE --skill github-triage -a codex`. Or copy the skill folder (skills/github-triage in ArabelaTso/Skills-4-SE) into .agents/skills/github-triage in your project. Codex loads it when a task matches its description.

Can I use GitHub Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill github-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-triage, .gemini/skills/github-triage, .github/skills/github-triage and .opencode/skills/github-triage in your project.

What does GitHub Triage need to run?

Going by SKILL.md and its folder, GitHub Triage needs the command-line tools its instructions call (gh and git).

Does GitHub Triage access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is GitHub Triage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does GitHub Triage use?

GitHub Triage is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GitHub Triage use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to GitHub Triage?

Skills that share tags, products or a category with GitHub Triage: Wayfinder (bestofjs/bestofjs, 3.1k stars), Setup Matt Pocock Skills (bestofjs/bestofjs, 3.1k stars), Windows App SDK Issue Triage Report (microsoft/WindowsAppSDK, 4.7k stars) and Exposed Bug Fix Workflow (JetBrains/Exposed, 9.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GitHub Triage?

ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 150 skills in this directory. The repository was last updated on August 21, 2026.

Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.